nasde-dev

Internal development guidance for changing nasde-toolkit, a Python toolkit for running and evaluating coding-agent tasks. It distinguishes the current toolkit from an older prototype and defines checks required after changes.

In plain words
What is it for?
Use it when modifying the toolkit’s command-line interface, task runner, evaluator, configuration, agents, dependencies, or integrations, then run its lint, format, type, and test checks.
Why use it?
It gives contributors a consistent process for editing the right code and verifying that changes are safe. This reduces stale references, broken integrations, and untested changes.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/noesisvision/nasde-toolkit/nasde-dev
Any agent
npx skills add NoesisVision/nasde-toolkit --skill nasde-dev
Clone the repo
git clone --depth 1 https://github.com/NoesisVision/nasde-toolkit

Made for: Claude Code, Codex.

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,965 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00103 $0.01965
Opus 5 $0.00051 $0.00983
Sonnet 5 $0.00021 $0.00393
Haiku 4.5 $0.00010 $0.00197

Measured 3d ago against content hash 1c26ee28fb16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nasde-dev scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

After any run with `--with-opik`, verify that all feedback scores arrived in Opik. Use Python `urllib.request` (never curl — it drops the `Comet-Workspace` header):
.claude/skills/nasde-dev/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NASDE Toolkit Development

Internal guidelines for developing nasde-toolkit itself.

Important context: nasde-toolkit/ is the current production toolkit. The repository also contains SDLC/evals/ which is the legacy predecessor — the original research/prototype that has been migrated into nasde-toolkit. Do NOT modify SDLC/evals/ for new work. It will be removed once migration is confirmed complete.

Post-change verification protocol

After any significant change to the toolkit (new features, refactors, dependency updates, renamed identifiers), run the full verification pipeline before considering the work complete.

1. Quality gates (must pass before any commit/PR)

These are the same checks that run on CI. Always run locally before claiming code is ready:

# Lint
uv run ruff check src/ tests/

# Format
uv run ruff format --check src/ tests/

# Type check
uv run mypy src/nasde_toolkit/

# Unit tests
uv run pytest

All four must pass. If ruff format fails, run uv run ruff format src/ tests/ to auto-fix.

After pushing, verify CI passes on the PR with gh pr checks <PR_NUMBER>.

1b. Static checks

# No stale references to old names or patterns
grep -r "sdlc.eval\|sdlc-eval\|sdlc_eval" src/ docs/ CLAUDE.md README.md .claude/skills/ pyproject.toml --include="*.py" --include="*.md" --include="*.toml" --include="*.json" | grep -v __pycache__

# Package installs cleanly
uv sync

1c. Documentation and skills consistency

After any change to the evaluation pipeline, CLI flags, configuration schema, agent support, or sandbox/environment handling, update all of these:

Definition of done — CHANGELOG first. A feature/fix is NOT complete until it has an entry under ## [Unreleased] in CHANGELOG.md. Add it as part of the change (same PR), never "at release time" — leaving it for later means the Unreleased section silently drifts behind the merged PRs and release notes go out wrong. This has happened (the section fell 5 PRs behind before v0.5.0). When finishing any user-visible work, the last step before declaring done is: does [Unreleased] describe it, in the right section, with a [#NN] link-ref?

Read the full file on GitHub · 162 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 162 lines · 103 tokens per session scan A 1c26ee28fb16

Subscribe to this mod's changes

nasde-dev is a skill published in the GitHub repository NoesisVision/nasde-toolkit (12 stars, last pushed 9d ago), licensed MIT. It adds 103 tokens to every session and 1,965 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.